您可以使用2D卷积构建一个掩码，根据该值选择值掩码，然后将它们减少到唯一值：

You can build a mask with a 2D convolution, select the values according to that mask, and then reduce them to unique values:

% // Data:
A = [ 1 1 1 1 1 1
      1 2 2 3 3 3
      4 4 2 2 3 3
      4 4 2 2 2 3
      4 4 4 4 3 3
      5 5 5 5 5 5 ];
value = 2;
adj = [0 1 0; 1 0 1; 0 1 0]; %// define adjacency. [1 1 1;1 0 1;1 1 1] to include diagonals

%// Let's go
mask = conv2(double(A==value), adj, 'same')>0; %// pixels adjacent to those equal to `value`
result = unique(A(mask));

在示例中，这会产生

result =
     1
     2
     3
     4

请注意，结果包括 2 ，因为某些值 2 的像素相邻具有该值的像素。

Note that the result includes 2 because some pixels with value 2 have adjacent pixels with that value.